fastmachinelearning / qonnxLinks
QONNX: Arbitrary-Precision Quantized Neural Networks in ONNX
☆150Updated this week
Alternatives and similar repositories for qonnx
Users that are interested in qonnx are comparing it to the libraries listed below
Sorting:
- Low Precision(quantized) Yolov5☆39Updated 3 months ago
- ☆149Updated 2 years ago
- PyTorch emulation library for Microscaling (MX)-compatible data formats☆247Updated last week
- Dataflow QNN inference accelerator examples on FPGAs☆218Updated 3 months ago
- The Riallto Open Source Project from AMD☆81Updated 2 months ago
- PyTorch extension for emulating FP8 data formats on standard FP32 Xeon/GPU hardware.☆110Updated 6 months ago
- CSV spreadsheets and other material for AI accelerator survey papers☆171Updated last year
- ☆100Updated last week
- Machine-Learning Accelerator System Exploration Tools☆168Updated 3 weeks ago
- Fork of upstream onnxruntime focused on supporting risc-v accelerators☆87Updated 2 years ago
- A tool to deploy Deep Neural Networks on PULP-based SoC's☆80Updated 4 months ago
- Open Source Compiler Framework using ONNX as Frontend and IR☆31Updated 2 years ago
- Accelergy is an energy estimation infrastructure for accelerator energy estimations☆143Updated last month
- Vitis HLS Library for FINN☆198Updated 3 weeks ago
- Torch2Chip (MLSys, 2024)☆52Updated 2 months ago
- Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts☆121Updated last year
- ONNXim is a fast cycle-level simulator that can model multi-core NPUs for DNN inference☆126Updated 4 months ago
- Quantized ResNet50 Dataflow Acceleration on Alveo, with PYNQ☆57Updated 3 years ago
- List of papers related to Vision Transformers quantization and hardware acceleration in recent AI conferences and journals.☆91Updated last year
- CHARM: Composing Heterogeneous Accelerators on Heterogeneous SoC Architecture☆143Updated this week
- Floating-Point Optimized On-Device Learning Library for the PULP Platform.☆34Updated last month
- Timeloop performs modeling, mapping and code-generation for tensor algebra workloads on various accelerator architectures.☆395Updated 2 weeks ago
- Repository to host and maintain scale-sim-v2 code☆308Updated 2 months ago
- NEural Minimizer for pytOrch☆43Updated 11 months ago
- PyTorch model to RTL flow for low latency inference☆127Updated last year
- IREE plugin repository for the AMD AIE accelerator☆97Updated this week
- ☆37Updated 3 years ago
- ☆30Updated 2 years ago
- DPU on PYNQ☆222Updated last year
- An open-source parameterizable NPU generator with full-stack multi-target compilation stack for intelligent workloads.☆57Updated 3 months ago